Triple
T16709058
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | WHDH-TV |
E406053
|
entity |
| Predicate | branding |
P1500
|
FINISHED |
| Object |
7News
7News is a television news brand used by WHDH-TV, a Boston-based independent station known for its local news coverage.
|
E1229731
|
NE FINISHED |
How this triple was built (4 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: 7News | Statement: [WHDH-TV, branding, 7News]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 7News Context triple: [WHDH-TV, branding, 7News]
-
A.
7NEWS Spotlight
7NEWS Spotlight is an Australian prime-time investigative and current affairs television program produced by the Seven Network, known for in-depth reports and exclusive interviews.
-
B.
5 News
5 News is the national news service for the UK television channel Channel 5, providing daily news coverage and current affairs programming.
-
C.
Stuff.co.nz
Stuff.co.nz is a major New Zealand news and media website providing national and international news, opinion, and multimedia content.
-
D.
Kāpiti News
Kāpiti News is a local community newspaper serving the Kāpiti Coast region of New Zealand, providing news, events, and information relevant to residents.
-
E.
Newsquest
Newsquest is a major regional newspaper and website publisher in the United Kingdom, operating numerous local titles across the country.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: 7News Triple: [WHDH-TV, branding, 7News]
Generated description
7News is a television news brand used by WHDH-TV, a Boston-based independent station known for its local news coverage.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: 7News Target entity description: 7News is a television news brand used by WHDH-TV, a Boston-based independent station known for its local news coverage.
-
A.
7NEWS Spotlight
7NEWS Spotlight is an Australian prime-time investigative and current affairs television program produced by the Seven Network, known for in-depth reports and exclusive interviews.
-
B.
5 News
5 News is the national news service for the UK television channel Channel 5, providing daily news coverage and current affairs programming.
-
C.
Stuff.co.nz
Stuff.co.nz is a major New Zealand news and media website providing national and international news, opinion, and multimedia content.
-
D.
Kāpiti News
Kāpiti News is a local community newspaper serving the Kāpiti Coast region of New Zealand, providing news, events, and information relevant to residents.
-
E.
Newsquest
Newsquest is a major regional newspaper and website publisher in the United Kingdom, operating numerous local titles across the country.
- F. None of above. chosen
Provenance (5 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d8838db21081909589220fd71440a4 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e38650c3808190a561f22b169dc3ae |
completed | April 18, 2026, 1:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0091a739308190b4d645e096d1710b |
completed | May 10, 2026, 2:09 p.m. |
| NEDg | Description generation | batch_6a00935ad86881908c45cdb513313a1d |
completed | May 10, 2026, 2:16 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a009a0bd7f8819090fb16d88108b96d |
completed | May 10, 2026, 2:45 p.m. |
Created at: April 10, 2026, 5:20 a.m.